© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11401
    Prev
    Next
    INDEX
    Explanations

    spontaneity, accident, or unplanned timing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ¯Ĵç´ł
    -0.21
     multiplic
    -0.19
     Ow
    -0.18
     Charg
    -0.18
    å¤ĸåĮħ
    -0.18
     пÑĢава
    -0.18
    å¤ĸç±į
    -0.17
    æĤĴ
    -0.17
     Dunk
    -0.17
     Mes
    -0.17
    POSITIVE LOGITS
    临æŶ
    0.34
    çªģåıij
    0.31
     spont
    0.28
    éļıæľº
    0.28
    å®ŀæŶ
    0.27
    èĩ¨
    0.27
    åºĶæĢ¥
    0.26
    unexpected
    0.26
    æĦıå¤ĸ
    0.26
    çİ°åľº
    0.25
    Activations Density 0.085%

    No Known Activations